Skills
Navigate
skills/thatrebeccarae/claude-marketing/email-composer/Gen Agent Trust Hub

email-composer

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting data from a brand profile.
  • Ingestion points: SKILL.md specifies reading brand-profile.json if it exists in the working directory.
  • Boundary markers: Absent; the skill does not define specific delimiters for the ingested JSON data.
  • Capability inventory: None; the skill performs no subprocess calls, file writes, or network operations across any files.
  • Sanitization: Absent; the skill relies on the model's internal safeguards for processing the ingested text.
  • [EXTERNAL_DOWNLOADS]: SKILL.md contains a git clone command for manual installation from the author's GitHub repository. This is a documented installation step for the user and does not represent an automated execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — email-composer